AVeryRealHuman/DialoGPT-small-TonyStark
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: AVeryRealHuman/DialoGPT-small-TonyStark
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-04 17:53:18 +08:00
commit 419b8ac8bb
21 changed files with 100134 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
.gitattributes vendored Normal file
View File

@@ -0,0 +1,27 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

6
README.md Normal file
View File

@@ -0,0 +1,6 @@
---
tags:
- conversational
---
#Tony Stark DialoGPT model

36
checkpoint-3500/config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"_name_or_path": "microsoft/DialoGPT-small",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"resid_pdrop": 0.1,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"conversational": {
"max_length": 1000
}
},
"torch_dtype": "float32",
"transformers_version": "4.11.3",
"use_cache": true,
"vocab_size": 50257
}

50001
checkpoint-3500/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-3500/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:295467549f74c93baa58e6a2f918f22bc0f9634e45fdc84d22e2069fa12748cf
size 995604017

3
checkpoint-3500/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b75f9e578f1c36e83d4a5d11d4e70316ec39dcbd5f520f140deb86ed72e76007
size 510403817

3
checkpoint-3500/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca69f26ca851482aa5e733edf6b287c938d0615ca676aef0c37476772f16d189
size 623

1
checkpoint-3500/special_tokens_map.json Normal file
View File

@@ -0,0 +1 @@
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

1
checkpoint-3500/tokenizer.json Normal file
View File

File diff suppressed because one or more lines are too long

1
checkpoint-3500/tokenizer_config.json Normal file
View File

@@ -0,0 +1 @@
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}

3
checkpoint-3500/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c6d265aeff90875caa5d8e5b5f580c945ef2104c7cb554c8633a881220518b4
size 1327

1
checkpoint-3500/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

36
config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"_name_or_path": "microsoft/DialoGPT-small",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"resid_pdrop": 0.1,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"conversational": {
"max_length": 1000
}
},
"torch_dtype": "float32",
"transformers_version": "4.11.3",
"use_cache": true,
"vocab_size": 50257
}

1
eval_results.txt Normal file
View File

@@ -0,0 +1 @@
perplexity = tensor(6.8862)

50001
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d4fc1364e98ffe98d4b4b5a7640d9c87a9cf5c3d7bae7b1c0d73c8c72b54474c
size 510403817

1
special_tokens_map.json Normal file
View File

@@ -0,0 +1 @@
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

1
tokenizer.json Normal file
View File

File diff suppressed because one or more lines are too long

1
tokenizer_config.json Normal file
View File

@@ -0,0 +1 @@
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c6d265aeff90875caa5d8e5b5f580c945ef2104c7cb554c8633a881220518b4
size 1327

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long